Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    code snippets and numbers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     greets
    0.41
     pulses
    0.41
     جگ
    0.38
    ulmonary
    0.38
     precon
    0.38
     पव
    0.36
     boulder
    0.36
    зона
    0.36
     hallways
    0.36
    ضرب
    0.36
    POSITIVE LOGITS
    Mist
    0.42
    it
    0.41
    ipin
    0.41
    League
    0.41
     İstanbul
    0.40
    gação
    0.40
    league
    0.40
    mist
    0.40
    ip
    0.39
    İstanbul
    0.39
    Act Density 0.008%

    No Known Activations